Prediction of soil chemical properties using multispectral satellite images and wavelet transforms methods

The main aim of this paper is to develop the accurately map of soil chemical parameters were used for development of the agriculture, forestry, ecological planning, and crop yield production. Soil chemical properties analysis and forecast model was developed and validated with the Wavelet transform methods and multispectral satellite images. At the study area sites, satellite images and soil samples were collected during a similar time. Three most important soil chemical properties such as organic carbon, pH and EC were chosen to development of predication modeling based on the soil chemical information. This valuable information of parameters was analysed according to conventional methods. The observed data of soil was used for the predication modeling of soil chemical properties by MATLAB software. The identification of soil chemical properties was the subject of multi-spectral satellite images through algorithm of soil predication modeling. The real chemical characteristics of the soil are associated to wavelet transformation methods. Forecasting of soil chemical properties and this model can be given more accurate information related to soil nutrient parameters. Now a day’s machine learning programming is an easy to applied on the natural resources and agriculture studies. The chemical characteristics of the soil are compared with the different spectrum wavelengths of the MATLAB program. Therefore, four wavelets models like Daubechies, Symlet, Biorthogonal and Coiflet were selected to development of predication modelling, which wavelet model can be given more accurate information with best model of the soil chemical properties. Also, the coefficient of five key components and soil-chemical values were associated in the MATLAB software. In the semi-arid regions in, India, which components have been highly correlated with soil parameters in the predicated modeling. More detailed information of soil chemical characteristics was provided by four selected wavelet models developed based on the observed data and satellite data. Prediction of soil chemical values has been identified through low and high-frequency satellite images and artificial neural network model. In this study, the neural network wavelet model was used to predicted values related to soil chemical properties in the semi-arid region. The developed two models, like polynomial and ANN, have been validated and compared to the soil chemical properties data, which models can be fitted with the study of soil chemical properties. The results of the study area can be more beneficial for development of agriculture activities, climate change approaches, crop and soil suitability planning. From the results of models have been given a fast and quickly information of soil nutrient parameters without laboratory analysis. The results of predicated values can be more helpful to precision farming related activates and soil fertility mapping to provide the farmers and agriculture scientist.